A Two-Step Named Entity Recognizer for Open-Domain Search Queries
Andreas Eiselt, Alejandro Figueroa · International Joint Conference on Natural Language Processing · 2013
Named entity recognition in queries is the task of identifying sequences of terms in search queries that refer to a unique concept. This problem is catching increasing attention, since the lack of context in short queries makes this task difficult for full-text off-the-shelf named entity recognizers. In this paper, we propose to deal with this problem in a two-step fashion. The first step classifies each query term as token or part of a named entity. The second step takes advantage of these binary labels for categorizing query terms into a pre-defined set of 28 named entity classes. Our results show that our two-step strategy is promising by outperforming a one-step traditional baseline by more than 10%.